Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of the sequence of underscores in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.69
    (
    -0.66
    "
    -0.66
    ,
    -0.66
    '
    -0.64
    {
    -0.59
    ";
    -0.59
     bur
    -0.58
    %
    -0.58
    \
    -0.57
    POSITIVE LOGITS
     myſelf
    1.04
     كومونز
    0.92
    OGND
    0.91
     feroit
    0.90
     becauſe
    0.90
     fhew
    0.88
     raiſ
    0.87
     EconPapers
    0.87
     itſelf
    0.87
     pouvoit
    0.86
    Act Density 0.263%

    No Known Activations